HOI Detection on V-COCO
72.1AP Role 1RLIPv2-ParSeDA
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RLIPv2-ParSeDABackbone=Swin-L, Extra Relations=VG+COCO+O3652023.08 | 72.1 | 74.1 | |
| RLIPv2-ParSeDBackbone=Swin-L, Extra Relations=VG+COCO+O3652023.08 | 71 | 73.2 | |
| RLIPv2-ParSeDABackbone=Swin-T, Extra Relations=VG+COCO+O3652023.08 | 68.8 | 70.8 | |
| DIFFUSIONHOIBackbone=ViT-L, VL Pretrain=Stable unCLIP2024.10 | 67.1 | 71.1 | |
| DIFFUSIONHOIBackbone=VQGAN, VL Pretrain=Stable Diffusion2024.10 | 66.8 | 70.9 | |
| RLIPv2-ParSeDBackbone=Swin-T, Extra Relations=VG+COCO+O3652023.08 | 66.6 | 69.1 | |
| CQLBackbone=R50, VL Pretrain=CLIP2024.10 | 66.4 | 69.2 | |
| STIPBackbone=R50, VL Pretrain=-2024.10 | 66 | 70.7 | |
| RLIPv2-ParSeDABackbone=R50, Extra Relations=VG+COCO+O3652023.08 | 65.9 | 68 | |
| UniVRDBackbone=ViT-H/14+, Extra Relations=-2023.08 | 65.8 | 66.9 | |
| AGERBackbone=R50, VL Pretrain=CLIP2024.10 | 65.7 | 69.7 | |
| RLIPv2-ParSeDABackbone=R50, Extra Relations=VG+COCO2023.08 | 64.5 | 66.7 | |
| OCNBackbone=R50, Extra Relations=-2023.08 | 64.2 | 66.3 | |
| RmLRBackbone=R101, VL Pretrain=MobileBERT2024.10 | 64.2 | 70.2 | |
| PViC†Backbone=Swin-L, VL Pretrain=-, detector=H-Deform-DETR [95]2024.10 | 64.1 | 70.2 | |
| CDNBackbone=R101, VL Pretrain=-2024.10 | 63.9 | 65.9 | |
| RLIPv2-ParSeDBackbone=R50, Extra Relations=VG+COCO+O3652023.08 | 63.8 | 66.4 | |
| GEN-VLKBackbone=R101, VL Pretrain=CLIP2024.10 | 63.6 | 65.9 | |
| HOICLIPBackbone=R50, VL Pretrain=CLIP2024.10 | 63.5 | 64.8 | |
| CPChoiBackbone=R50, VL Pretrain=-2024.10 | 63.1 | 65.4 | |
| RLIPv2-ParSeDABackbone=R50, Extra Relations=VG2023.08 | 63 | 65.1 | |
| MCPCBackbone=R50, VL Pretrain=-2024.10 | 63 | 65.1 | |
| RLIPv2-ParSeDBackbone=R50, Extra Relations=VG+COCO2023.08 | 62.9 | 65.3 | |
| PViCBackbone=R50, VL Pretrain=-2024.10 | 62.8 | 67.8 | |
| GEN-VLKTBackbone=R50, Extra Relations=-2023.08 | 62.4 | 64.5 | |
| ViPLOBackbone=ViT-B, VL Pretrain=CLIP2024.10 | 62.2 | 68 | |
| RLIPv1-ParSeBackbone=R50, Extra Relations=VG2023.08 | 61.9 | 64.2 | |
| RLIPv2-ParSeDBackbone=R50, Extra Relations=VG2023.08 | 61.9 | 64.5 | |
| CDNBackbone=R50, Extra Relations=-2023.08 | 61.7 | 63.8 | |
| RLIPv1-ParSeDBackbone=R50, Extra Relations=VG2023.08 | 61.7 | 63.8 | |
| UPTBackbone=R101, VL Pretrain=-2024.10 | 61.3 | 67.1 | |
| IwinBackbone=R101, VL Pretrain=-2024.10 | 60.9 | — | |
| QPICBackbone=R50, Extra Relations=-2023.08 | 58.8 | 61 | |
| ADA-CMBackbone=ViT-L, VL Pretrain=CLIP2024.10 | 58.6 | 64 | |
| QPICBackbone=R101, VL Pretrain=-2024.10 | 58.3 | 60.7 | |
| HOTRBackbone=R50, Extra Relations=-2023.08 | 55.2 | 64.4 | |
| HOTRBackbone=R50, VL Pretrain=-2024.10 | 55.2 | 64.4 | |
| UnionDetBackbone=R50-FPN, Extra Relations=-2023.08 | 47.5 | 56.2 | |
| ICANBackbone=R50, VL Pretrain=-2024.10 | 45.3 | — | |
| InteractNetBackbone=R50-FPN, Extra Relations=-2023.08 | 40 | — |